Kensho Kclub

io.github.atushi1841v1.0.0Updated Oct 3, 2026

Japan X/Twitter sweepstakes data from kenshou.club. Tools: search, history, prize movers.

VerifiedSTDIODesktop onlyData & AnalyticsWeb Search & Scraping

Overview

AI-generated overview

Read-only access to a Japanese X/Twitter sweepstakes dataset, letting an assistant look up current giveaways, prize history, and biggest prize movers.

What it does
Exposes the kenshou.club Japan X/Twitter sweepstakes dataset through three read-only tools. current_sweep returns the latest sweep matching a keyword such as a prize, brand, or URL substring. sweep_history returns a prize time series for a keyword, oldest first, with a configurable limit. top_prize_movers ranks entries by absolute change in prize value in yen, optionally filtered to increases or decreases.
When to use it
Useful when you want an assistant to answer questions about Japanese X/Twitter sweepstakes campaigns, track how a prize value has changed over time, or surface the campaigns whose prize values moved most. It is a niche, read-only data source rather than a general search tool.
Requirements
Runs locally as a stdio MCP process and is desktop only. Requires Python and the fastmcp package version 3.0.0 or later. No network access, API key, or account is required, and no environment variables or headers are declared.
Before you install
The dataset is a bundled snapshot dated 2026-09-28 with an estimated 100+ observations, so results may be stale and are not live. All tools are read-only and no credentials are requested. The README describes a revenue-sharing model tied to external queries, which is worth noting but does not affect local use.

Installation

In SourceWeft

  1. Open Kensho Kclub in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

kensho-kclub — Kenshou Club Sweepstakes MCP Server

Read-only MCP server exposing the kensho Japan X/Twitter sweepstakes dataset from kenshou.club (additional sweepstakes source for Kensho collection).

Tools

ToolDescription
current_sweep(keyword)Latest sweep matching keyword (prize, brand, URL substring)
sweep_history(keyword, limit=50)Price time series (oldest first)
top_prize_movers(direction=None, limit=10)Biggest

Data

  • Source: data/accumulated.jsonl (estimated 100+ observations, snapshot 2026-09-28)
  • Source: kenshou.club sweepstakes archives (tagged "twitterで応募", up to 24 pages)
  • No network, no API key, no account required

Run

bash
python server/server.py          # stdio MCP transportpython server/server.py --http   # streamable-http at /mcp

Requires fastmcp>=3.0.0 (see requirements.txt).

MCP Bundle

manifest.json follows the MCPB v0.4 spec. Pack with:

bash
npx -y @anthropic-ai/mcpb pack . dist/kensho-kclub.mcpb

Revenue Model

This MCP Connector follows the Kensho revenue sharing model:

  • 20% to Apify (platform fee)
  • PPE model continues for internal operations
  • Revenue generated from external queries via Apify MCP integration

Integration Notes

The kensho-kclub MCP Connector serves as an additional data source for the main Kensho sweepstakes collection, complementing the existing knshow.com, ken-kaku.com, kenshou.club, and cp.meikan.org sources. It provides specialized coverage of the Kenshou.club sweepstakes ecosystem with 24 pages of archives tagged with "twitterで応募".

Source: README.md at commit 04694c8

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v1.0.0LatestOct 3, 2026